Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Elliott, Chris, Murfet, Daniel
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910201979863040
author Elliott, Chris
Murfet, Daniel
author_facet Elliott, Chris
Murfet, Daniel
contents These notes introduce the theory of susceptibilities as developed in [arXiv:2504.18274, arXiv:2601.12703] for interpreting neural networks. The susceptibility of an observable $ϕ$ to a data perturbation is defined as a derivative of a posterior expectation, which by the fluctuation--dissipation theorem equals a posterior covariance. Different choices of $ϕ$ yield different objects: per-sample losses give the influence matrix (the Bayesian influence function of [arXiv:2509.26544]), while component-localized observables give the structural susceptibility matrix that pairs model components with data patterns. The susceptibility matrix is (up to a factor of $nβ$) the Jacobian of the map from data distributions to structural coordinates; its pseudo-inverse provides a linearized solution to the patterning problem of [arXiv:2601.13548]: finding data perturbations that produce a desired structural change. We motivate the theory from its statistical-mechanical foundations, then give a detailed exposition of susceptibilities, their empirical estimators, and their connection to the geometry of the loss landscape.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07980
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
Elliott, Chris
Murfet, Daniel
Machine Learning
Statistical Mechanics
Statistics Theory
These notes introduce the theory of susceptibilities as developed in [arXiv:2504.18274, arXiv:2601.12703] for interpreting neural networks. The susceptibility of an observable $ϕ$ to a data perturbation is defined as a derivative of a posterior expectation, which by the fluctuation--dissipation theorem equals a posterior covariance. Different choices of $ϕ$ yield different objects: per-sample losses give the influence matrix (the Bayesian influence function of [arXiv:2509.26544]), while component-localized observables give the structural susceptibility matrix that pairs model components with data patterns. The susceptibility matrix is (up to a factor of $nβ$) the Jacobian of the map from data distributions to structural coordinates; its pseudo-inverse provides a linearized solution to the patterning problem of [arXiv:2601.13548]: finding data perturbations that produce a desired structural change. We motivate the theory from its statistical-mechanical foundations, then give a detailed exposition of susceptibilities, their empirical estimators, and their connection to the geometry of the loss landscape.
title Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
topic Machine Learning
Statistical Mechanics
Statistics Theory
url https://arxiv.org/abs/2605.07980